Agile V Skills – Open skills for verifiable, traceable AI engineering
Enforces test independence in AI agents to break the confirmation bias loop.

Another coding assessment platform in a market dominated by HackerRank and LeetCode.
Software engineers and technical hiring managers
HackerRank · Codility · Credly
Enforces test independence in AI agents to break the confirmation bias loop.
They split responsibilities across isolated agents (engineer, reviewer, manager) that get real shell access and independent filesystems, which makes failures traceable and lets you tune model capacity per role. Hitting 72.2% on SWE-bench Verified with no benchmark-specific tuning is an impressive empirical result — interesting architecture and strong evidence — though the security and long-term reliability of autonomous shell-executing agents remain the big open questions.
SDLC governance scanner that maps GitHub activity to SOC 2 and ISO 27001 controls.
Blog post comparing AI reverse engineering skills, not an actual tool or product.
Spreadsheet replacement for team skill matrices, but HR systems like Lattice already solve this.
Structured technical specs that sync directly to engineering issues.